© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68360
    Prev
    Next
    INDEX
    Explanations

    product model numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags tokens that contain digits—e.g. numeric measurements, model or version numbers, years, screen sizes, and other alphanumeric specs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     testSet
    -1.22
     rodillas
    -1.14
    anillo
    -1.12
     disponibile
    -1.11
    pette
    -1.09
     the
    -1.09
    πως
    -1.09
     sabid
    -1.08
    .”
    -1.06
    ḇ
    -1.06
    POSITIVE LOGITS
     عندما
    1.27
     Sebelum
    1.16
    karena
    1.14
    Kenapa
    1.10
    Sebelum
    1.09
    Hanya
    1.09
     Semoga
    1.05
     również
    1.04
    Spesifikasi
    1.03
    Penulis
    1.02
    Activations Density 0.042%

    No Known Activations